From 96a476a2331daa4d1d6b5ac444bbdbd2ac221a5f Mon Sep 17 00:00:00 2001
From: Christoph Helma <helma@in-silico.ch>
Date: Thu, 10 Sep 2015 12:54:18 +0200
Subject: tests fixed (crossvalidations may fail due to memory constraints)

---
 lib/compound.rb   | 12 +++---------
 lib/dataset.rb    | 32 +-------------------------------
 lib/experiment.rb |  4 ++--
 lib/model.rb      |  7 +++++--
 lib/overwrite.rb  |  4 ++++
 5 files changed, 15 insertions(+), 44 deletions(-)

(limited to 'lib')

diff --git a/lib/compound.rb b/lib/compound.rb
index 8f393f5..6adf3c0 100644
--- a/lib/compound.rb
+++ b/lib/compound.rb
@@ -218,11 +218,6 @@ module OpenTox
         obconversion.write_string(obmol).gsub(/\s/,'').chomp
       when /sdf/
 p "SDF conversion"
-        # has no effect
-	#obconversion.add_option("gen3D", OpenBabel::OBConversion::GENOPTIONS)
-        # segfaults with openbabel git master 
-        #OpenBabel::OBOp.find_type("Gen3D").do(obmol) 
-
         # TODO: find disconnected structures
         # strip_salts
         # separate
@@ -234,14 +229,13 @@ p "SDF conversion"
 print sdf
         if sdf.match(/.nan/)
           
-# TODO: fix or eliminate 2d generation
           $logger.warn "3D generation failed for compound #{identifier}, trying to calculate 2D structure"
           obconversion.set_options("gen2D", OpenBabel::OBConversion::GENOPTIONS)
-          #OpenBabel::OBOp.find_type("Gen2D").do(obmol) 
           sdf = obconversion.write_string(obmol)
           if sdf.match(/.nan/)
-            $logger.warn "2D generation failed for compound #{identifier}"
-            sdf = nil
+            $logger.warn "2D generation failed for compound #{identifier}, rendering without coordinates."
+            obconversion.remove_option("gen2D", OpenBabel::OBConversion::GENOPTIONS)
+            sdf = obconversion.write_string(obmol)
           end
         end
         sdf
diff --git a/lib/dataset.rb b/lib/dataset.rb
index 28d2120..851fabd 100644
--- a/lib/dataset.rb
+++ b/lib/dataset.rb
@@ -151,7 +151,7 @@ module OpenTox
       name = File.basename(file,".*")
       dataset = self.find_by(:source => source, :name => name)
       if dataset
-        $logger.debug "#{file} already in database."
+        $logger.debug "Skipping #{file}, it is already in the database (id: #{dataset.id})."
       else
         $logger.debug "Parsing #{file}."
         table = CSV.read file, :skip_blanks => true
@@ -270,36 +270,6 @@ module OpenTox
 
     end
 
-=begin
-    # TODO remove
-
-    # Create a dataset with compounds and features
-    def self.create compounds, features, warnings=[], source=nil
-      dataset = Dataset.new(:warnings => warnings)
-      dataset.compounds = compounds
-      dataset.features = features
-      dataset
-    end
-    # merge dataset (i.e. append features)
-    def +(dataset)
-      bad_request_error "Dataset merge failed because the argument is not a OpenTox::Dataset but a #{dataset.class}" unless dataset.is_a? Dataset
-      bad_request_error "Dataset merge failed because compounds are unequal in datasets #{self.id} and #{dataset.id}" unless compound_ids == dataset.compound_ids
-      self.feature_ids ||= []
-      self.feature_ids = self.feature_ids + dataset.feature_ids
-      @data_entries ||= Array.new(compound_ids.size){[]}
-      @data_entries.each_with_index do |row,i|
-        @data_entries[i] = row + dataset.fingerprint(compounds[i])
-      end
-      self
-
-    end
-
-    def fingerprint(compound)
-      i = compound_ids.index(compound.id)
-      i.nil? ? nil : data_entries[i] 
-    end
-=end
-
     # Fill unset data entries 
     # @param any value
     def fill_nil_with n
diff --git a/lib/experiment.rb b/lib/experiment.rb
index 191e76e..2f51756 100644
--- a/lib/experiment.rb
+++ b/lib/experiment.rb
@@ -34,7 +34,7 @@ module OpenTox
               if cv
                 $logger.debug "Creating #{cv} for #{model_algorithm}, dataset #{dataset.name}, with prediction_algorithm #{prediction_algorithm}, neighbor_algorithm #{neighbor_algorithm}, neighbor_algorithm_parameters #{neighbor_algorithm_parameter}."
                 crossvalidation = cv.create model
-                crossvalidation_ids << crossvalidation.id
+                self.crossvalidation_ids << crossvalidation.id
               else
                 $logger.warn "#{dataset.features.first} is neither nominal nor numeric."
               end
@@ -55,7 +55,7 @@ module OpenTox
 
   def report
     # TODO create ggplot2 report
-    crossvalidation_ids.each do |id|
+    self.crossvalidation_ids.each do |id|
       cv = CrossValidation.find(id)
       file = "/tmp/#{id}.svg"
       File.open(file,"w+"){|f| f.puts cv.correlation_plot}
diff --git a/lib/model.rb b/lib/model.rb
index 36011a0..547144f 100644
--- a/lib/model.rb
+++ b/lib/model.rb
@@ -138,16 +138,19 @@ module OpenTox
     end
 
     class LazarFminerClassification < LazarClassification
-      def self.create training_dataset
+      field :feature_calculation_parameters, type: Hash
+
+      def self.create training_dataset, fminer_params={}
         model = super(training_dataset)
         model.update "_type" => self.to_s # adjust class
         model = self.find model.id # adjust class
         model.neighbor_algorithm = "OpenTox::Algorithm::Neighbor.fminer_similarity"
         model.neighbor_algorithm_parameters = {
           :feature_calculation_algorithm => "OpenTox::Algorithm::Descriptor.smarts_match",
-          :feature_dataset_id => Algorithm::Fminer.bbrc(training_dataset).id,
+          :feature_dataset_id => Algorithm::Fminer.bbrc(training_dataset,fminer_params).id,
           :min_sim => 0.3
         }
+        model.feature_calculation_parameters = fminer_params
         model.save
         model
       end
diff --git a/lib/overwrite.rb b/lib/overwrite.rb
index cb47527..08baa39 100644
--- a/lib/overwrite.rb
+++ b/lib/overwrite.rb
@@ -122,4 +122,8 @@ module URI
     false
   end
 
+  def self.task? uri
+    uri =~ /task/ and URI.valid? uri
+  end
+
 end
-- 
cgit v1.2.3